Home / codenamev / ai-software-architect · skills/architecture-review/SKILL.md · GitHub

architecture-review skillA

architecture-review is agent-read markdown (skill) from codenamev/ai-software-architect: Conducts a comprehensive multi-perspective architecture review using ALL architecture team members. Use when the user requests "Start architecture review", "Full architecture review", "Review architecture for version X.Y.Z", "Conduct comprehensive review", or when they want assessment from multiple perspectives. Do NOT use for single-specialist reviews (use specialist-review instead) or for status checks (use architecture-status instead)..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Architecture Review (orchestrator)

Comprehensive multi-perspective architecture review. This skill is an **orchestrator** — it dispatches one subagent invocation per active team member in parallel, then aggregates the returned reviews into a consolidated document. The deep-perspective work happens in the subagents (`agents/<id>.md`), not in this skill's main thread.

See [ADR-013](../../.architecture/decisions/adrs/ADR-013-skill-orchestrator-subagent-delegation.md) for the rationale.

## Process

### 1. Determine scope

Identify the review target from the user's request:
- **Version** — "version 2.0.0" → filename `2-0-0.md`
- **Feature** — "authentication feature" → filename `feature-authentication.md`
- **Component** — "payments module" → filename `component-payments-module.md`

Apply input sanitization from [`../_patterns.md`](../_patterns.md). If the scope is ambiguous, ask one clarifying question and stop.

### 2. Load team and config

Read `.architecture/config.yml` and `.architecture/members.yml`:

- `config.yml.pragmatic_mode.enabled` decides whether to include the `pragmatic_enforcer` subagent.
- `members.yml.members[]` is the list of subagents to dispatch.
…

Read the whole file at its exact version.

How to install

Latest version
mdr add codenamev/ai-software-architect/architecture-review@git:20260504.de7ccc8
Exact content
mdr add codenamev/ai-software-architect/architecture-review@sha256:91ff8727d6629539

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_4dypydbrpgzwpeli.svg)](https://markdownregistry.com/a/art_4dypydbrpgzwpeli)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260504.de7ccc8 latest2026-05-04 de7ccc8 7,490 BA view · diff
git:20260504.27ad56d2026-05-04 27ad56d 4,707 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (7490 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

codenamev/ai-software-architect · 78 stars · license none · pushed 2026-09-19 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_4dypydbrpgzwpeli
GET https://markdownregistry.com/api/v1/resolve?ref=codenamev/ai-software-architect/architecture-review
GET https://markdownregistry.com/api/v1/blob/91ff8727d6629539debd9cfb084e3fdc415178dbb2fa7da5838c1b1cc94093fd

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from codenamev/ai-software-architect

AGENTS.md@.architecture/templates agents
codenamev/ai-software-architect · .architecture/templates/AGENTS.md
git:20251204.37685d4 · audit A · 78 stars
CLAUDE.md@.coding-assistants/claude claude
codenamev/ai-software-architect · .coding-assistants/claude/CLAUDE.md
git:20250523.71cdbef · audit A · 78 stars
AGENTS.md agents
codenamev/ai-software-architect · AGENTS.md
git:20260819.01d777e · audit A · 78 stars
CLAUDE.md claude
codenamev/ai-software-architect · CLAUDE.md
git:20260723.a1c9603 · audit A · 78 stars
architecture-status skill
codenamev/ai-software-architect · skills/architecture-status/SKILL.md · Reports on the health and state of architecture documentation (counts of ADRs, reviews, activity levels, documentation…
git:20260504.27ad56d · audit A · 78 stars
create-adr skill
codenamev/ai-software-architect · skills/create-adr/SKILL.md · Creates a NEW Architectural Decision Record (ADR) documenting a specific architectural decision. Use when the user…
git:20260504.d1d5014 · audit A · 78 stars
list-members skill
codenamev/ai-software-architect · skills/list-members/SKILL.md · Displays the roster of architecture team members with their specialties and expertise areas. Use when the user asks…
git:20260504.27ad56d · audit A · 78 stars
pragmatic-guard skill
codenamev/ai-software-architect · skills/pragmatic-guard/SKILL.md · Enables and configures Pragmatic Guard Mode (YAGNI Enforcement) to prevent over-engineering. Use when the user requests…
git:20260504.d1d5014 · audit A · 78 stars
setup-architect skill
codenamev/ai-software-architect · skills/setup-architect/SKILL.md · Sets up and installs the AI Software Architect framework in a NEW project for the FIRST time. Use when the user…
git:20260723.a1c9603 · audit A · 78 stars
specialist-review skill
codenamev/ai-software-architect · skills/specialist-review/SKILL.md · Conducts a focused review from ONE specific specialist's perspective (e.g., Security Specialist, Performance Expert)…
git:20260504.de7ccc8 · audit A · 78 stars

Every file in codenamev/ai-software-architect

Other files named architecture-review

architecture-review skill
sickn33/agentic-awesome-skills · plugins/agentic-awesome-skills-claude/skills/architecture-review/SKILL.md · Review repository architecture using Ontoly Software Graph and MCP capabilities.
git:20260921.9164115 · audit A · 46,848 stars
architecture-review skill
decebals/claude-code-java · skills/architecture-review/SKILL.md · Analyze Java project architecture at macro level - package structure, module boundaries, dependency direction, and…
git:20260828.702770a · audit A · 744 stars

Browse by kind, by grade A, or by owner.